Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    中新
    -0.07
     vocabulary
    -0.07
    不幸
    -0.07
    ittest
    -0.07
     intertwined
    -0.06
    imgs
    -0.06
    مضي
    -0.06
    .imp
    -0.06
    credit
    -0.06
    .take
    -0.06
    POSITIVE LOGITS
     malls
    0.08
     democrat
    0.07
    odega
    0.07
     Joker
    0.07
     Cuomo
    0.07
    体现了
    0.07
    _processing
    0.07
     Hond
    0.06
     cabin
    0.06
     gp
    0.06
    Act Density 0.002%

    No Known Activations